CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gstack-upgrade

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced operational skill with copy-paste bash for every branch, held back by validation gaps around destructive operations (unconditional backup deletion, unverified `git reset --hard`) and minor dead-code/redundancy. Structure is good for a single-file skill, though its length invites some splitting into references.

Suggestions

Verify `./setup` succeeds before deleting the backup in the vendored path — gate `rm -rf "$INSTALL_DIR.bak"` on the setup exit code, mirroring the restore-on-failure handling already present in the auto-upgrade and Step 4.5 paths.

Add a post-upgrade verification checkpoint (e.g., compare `$INSTALL_DIR/VERSION` to the expected new version) before declaring success and before `git reset --hard`-based paths discard state.

Remove the duplicated `elif [ -d ".agents/skills/gstack/.git" ]` branch in Step 2 (dead code that wastes tokens) and consider moving the snooze-backoff and standalone-usage detail into reference files.

DimensionReasoningScore

Conciseness

The body is operational throughout — every step is a runnable bash block with terse directive prose and no explanation of concepts Claude already knows. It falls short of a 5 because of a duplicated dead `elif [ -d ".agents/skills/gstack/.git" ]` branch in Step 2 and repeated navigational restatements like 'Use the install directory from Step 2's output below'.

4 / 5

Actionability

Every step provides fully executable, copy-paste-ready bash (install detection, version save, git/vendored upgrade, snooze backoff, sync), and the branches cover the common cases including all four AskUserQuestion options and failure-restore paths. Not below 5: placeholders like {old}/{new} are explicitly explained, so nothing is left as vague direction or pseudocode.

5 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced and some failure-restore loops exist (auto-upgrade setup failure, Step 4.5 sync failure), but destructive operations lack validation in several paths: the vendored path runs `rm -rf "$INSTALL_DIR.bak"` unconditionally even if `./setup` failed, and the manual git path has no checkpoint after `git reset --hard origin/main`. The rubric's cap — destructive workflows with missing validation cannot score above 3 — applies, so this does not reach 4 despite the strong sequencing.

3 / 5

Progressive Disclosure

No bundle files exist; the single body uses well-organized, clearly headed step sections with no nested references, and the inline upgrade flow is deliberately inline for preamble reuse. Not 5: at ~220 lines, content such as the snooze-backoff script and the standalone-usage section could be split into reference files.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A model description: concrete third-person actions covering the complete upgrade lifecycle, paired with an explicit 'Use when' clause quoting the exact natural trigger phrases. Specific, complete, and highly distinctive with negligible conflict risk.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the skill's full lifecycle — 'Detects global vs vendored install, runs the upgrade, and shows what's new' — in third-person voice. Coverage is comprehensive for this single-tool domain, so it fits the 5 anchor rather than the 4 anchor's 'minor gaps'.

5 / 5

Completeness

It explicitly answers both questions: 'what' (detect install type, run the upgrade, show what's new) and 'when' ('Use when asked to "upgrade gstack", "update gstack", or "get latest version"') with concrete trigger phrases — the exact pattern of the 5 anchor example. A 4 would require the 'when' clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

It quotes the natural phrases a user would actually say — 'upgrade gstack', 'update gstack', 'get latest version' — covering the complete synonym set (upgrade/update/latest) for this action. Nothing relevant is missing, matching the 5 anchor's comprehensive synonym coverage.

5 / 5

Distinctiveness Conflict Risk

The description targets a clear niche (the specific tool 'gstack') with tool-named triggers, so overlap risk with other skills is minimal — matching the 5 anchor's 'clear niche with distinct triggers'.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

valeriibeck-star/claude-skills

Path

skills/gstack/.agents/skills/gstack-upgrade/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.